Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 21273
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xúc
    -0.07
     Correction
    -0.06
     decryption
    -0.06
    Repositories
    -0.06
    _zone
    -0.06
     Basin
    -0.06
     hardest
    -0.06
     chân
    -0.06
     Acid
    -0.06
     endl
    -0.06
    POSITIVE LOGITS
    िज
    0.08
    нг
    0.07
    าล
    0.07
    すぎ
    0.07
     труд
    0.07
    strand
    0.06
    	↵	↵	↵	↵
    0.06
    928
    0.06
    rts
    0.06
    ينات
    0.06
    Activations Density 0.028%

    No Known Activations